Abstract
Recent research has proposed the evolutionary-gradient-search procedure that uses the evolutionary scheme to estimate a gradient direction and that performs the parameter updates in a steepest-descent form. On several test functions, the procedure has shown faster convergence than other evolutionary algorithms. However, the procedure also exhibits similar deficiencies as steepest-descent methods. This paper explores to which extent the adoption of individual step sizes, as known from evolution strategies, can be beneficially used. It turns out that they considerably accelerate convergence.
Preview
Unable to display preview. Download preview PDF.
References
Bäck, T., Schwefel, H.-P.: An Overview of Evolutionary Algorithms for Parameter Optimization. Evolutionary Computation 1(1) (1993) 1–23
Bäck, T., Kursawe, F.: Evolutionary Algorithms for Fuzzy Logic: A Brief Overview. In: Bouchon-Meunier, B., Yager, R.R., Zadeh, L.A. (eds.): Fuzzy Logic and Soft Computing, Vol. IV. World Scientific, Singapore (1995) 3–10
Beyer, H.-G.: An Alternative Explanation for the Manner in which Genetic Algorithms Operate. BioSystems 41 (1997) 1–15
Fogel, D.B.: Evolutionary Computation: Toward a New Philosophy of Machine Learning Intelligence. IEEE Press, Jersy, NJ (1995)
Fogel, L.J.: “Autonomous Automata”. Industrial Research 4 (1962) 14–19
Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Publishing Company (1989)
Hansen, N., Ostermeier, A.: Adapting Arbitrary Normal Mutation Distributions in Evolution Strategies: The Covariance Matrix Adaptation. In: Proceedings of The 1996 IEEE International Conference on Evolutionary Computation (IECEC'96). IEEE (1996) 312–317
Hansen, N., Ostermeier, A.: Convergence Properties of Evolution Strategies with the Derandomized Covariance Matrix Adaptation: The (Μ/Μ I, λ)-CMA-ES. In: Zimmermann, H.-J. (ed.): Proceedings of The Fifth Congress on Intelligent Techniques and Soft Computing EUFIT'97. Verlag Mainz, Achen, (1997) 650–654
Luenberger, D.G.: Linear and Nonlinear Programming. Addison-Wesley, Menlo Park, CA (1984)
Mühlenbein, H., Schlierkamp-Voosen, D.: Predictive Models for the Breeder Genetic Algorithm I. Evolutionary Computation 1(1) (1993) 25–50.
Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C. Cambridge University Press, Cambridge, UK (1994)
Rechenberg, I.: Evolutionsstrategie. Frommann-Holzboog, Stuttgart (1994)
Rumelhart et al. (eds.): Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 2. The MIT Press, Cambridge, MA (1986)
Salomon, R.: Reevaluating Genetic Algorithm Performance under Coordinate Rotation of Benchmark Functions; A survey of some theoretical and practical aspects of genetic algorithms. BioSystems 39(3) (1996) 263–278
Salomon, R.: The Evolutionary-Gradient-Search Procedure. In: Koza, J. et al. (eds.): Genetic Programming 1998: Proceedings of the Third Annual Conference, July 22–25, 1998. Morgan Kaufmann, San Francisco, CA (1998)
Salomon, R., van Hemmen, J.L.: Accelerating backpropagation through dynamic self-adaptation. Neural Networks 9(4) (1996) 589–601
Schwefel, H.-P.: Evolution and Optimum Seeking. John Wiley and Sons, NY (1995)
Schwefel, H.-P.: Evolutionary Computation — A Study on Collective Learning. In: Callaos, N., Khoong, C.M., Cohen, E. (eds.): Proceedings of the World Multiconference on Systemics, Cybernetics and Informatics, vol. 2. Int'l Inst. of Informatics and Systemics, Orlando FL (1997) 198–205
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Salomon, R. (1998). Accelerating the evolutionary-gradient-search procedure: Individual step sizes. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, HP. (eds) Parallel Problem Solving from Nature — PPSN V. PPSN 1998. Lecture Notes in Computer Science, vol 1498. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0056883
Download citation
DOI: https://doi.org/10.1007/BFb0056883
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65078-2
Online ISBN: 978-3-540-49672-4
eBook Packages: Springer Book Archive